| import time | |
| import streamlit as st | |
| from transformers import pipeline | |
| import os | |
| import torch | |
| import datetime | |
| import numpy as np | |
| import soundfile | |
| from wavmark.utils import file_reader | |
| # pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog") | |
| # st.title("Hot Dog? Or Not?") | |
| # file_name = st.file_uploader("Upload a hot dog candidate image") | |
| # if file_name is not None: | |
| # col1, col2 = st.columns(2) | |
| # image = Image.open(file_name) | |
| # col1.image(image, use_column_width=True) | |
| # predictions = pipeline(image) | |
| # col2.header("Probabilities") | |
| # for p in predictions: | |
| # col2.subheader(f"{ p['label'] }: { round(p['score'] * 100, 1)}%") | |
| def create_default_value(): | |
| if "def_value" not in st.session_state: | |
| def_val_npy = np.random.choice([0, 1], size=32 - len_start_bit) | |
| def_val_str = "".join([str(i) for i in def_val_npy]) | |
| st.session_state.def_value = def_val_str | |
| # Main web app | |
| def main(): | |
| create_default_value() | |
| # st.title("MDS07") | |
| # st.write("https://github.com/wavmark/wavmark") | |
| markdown_text = """ | |
| # MDS07 | |
| [AudioSeal](https://github.com/jcha0155/AudioSealEnhanced) is the next-generation watermarking tool driven by AI. | |
| You can upload an audio file and encode a custom 16-bit watermark or perform decoding from a watermarked audio. | |
| This page is for demonstration usage and only process **the first minute** of the audio. | |
| If you have longer files for processing, we recommend using [our python toolkit](https://github.com/jcha0155/AudioSealEnhanced). | |
| """ | |
| # 使用st.markdown渲染Markdown文本 | |
| st.markdown(markdown_text) | |
| audio_file = st.file_uploader("Upload Audio", type=["wav", "mp3"], accept_multiple_files=False) | |
| if audio_file: | |
| # 保存文件到本地： | |
| tmp_input_audio_file = os.path.join("/tmp/", audio_file.name) | |
| with open(tmp_input_audio_file, "wb") as f: | |
| f.write(audio_file.getbuffer()) | |
| # 展示文件到页面上 | |
| # st.audio(tmp_input_audio_file, format="audio/wav") | |
| action = st.selectbox("Select Action", ["Add Watermark", "Decode Watermark"]) | |
| # if action == "Add Watermark": | |
| # watermark_text = st.text_input("The watermark (0, 1 list of length-16):", value=st.session_state.def_value) | |
| # add_watermark_button = st.button("Add Watermark", key="add_watermark_btn") | |
| # if add_watermark_button: # 点击按钮后执行的 | |
| # if audio_file and watermark_text: | |
| # with st.spinner("Adding Watermark..."): | |
| # watermarked_audio, encode_time_cost = add_watermark(tmp_input_audio_file, watermark_text) | |
| # st.write("Watermarked Audio:") | |
| # print("watermarked_audio:", watermarked_audio) | |
| # st.audio(watermarked_audio, format="audio/wav") | |
| # st.write("Time Cost: %d seconds" % encode_time_cost) | |
| # # st.button("Add Watermark", disabled=False) | |
| # elif action == "Decode Watermark": | |
| # if st.button("Decode"): | |
| # with st.spinner("Decoding..."): | |
| # decode_watermark(tmp_input_audio_file) | |
| if __name__ == "__main__": | |
| # default_sr = 16000 | |
| # max_second_encode = 60 | |
| # max_second_decode = 30 | |
| # len_start_bit = 16 | |
| # device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu') | |
| # model = wavmark.load_model().to(device) | |
| main() | |
| # audio_path = "/Users/my/Library/Mobile Documents/com~apple~CloudDocs/CODE/PycharmProjects/4_语音水印/419_huggingface水印/WavMark/example.wav" | |
| # decoded_watermark, decode_cost = decode_watermark(audio_path) | |
| # print(decoded_watermark) |